CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization
By Sungwook Lee, Seunghyun Lee, Byung Cheol Song. IEEE Access, 2022
336 citations recorded by the source corpus.
For a long time, anomaly localization has been widely used in industries. Previous studies focused on approximating the distribution of normal features without adaptation to a target dataset. However, since anomaly localization should precisely discriminate between normal and abnormal features, the absence of adaptation may make the normality of abnormal features overestimated. Thus, we propose Coupled-hypersphere-based Feature Adaptation (CFA) which accomplishes sophisticated anomaly localization using features adapted to the target dataset. CFA consists of (1) a learnable patch descriptor that learns and embeds target-oriented features and (2) a scalable memory bank independent of the size of the target dataset. And, CFA adopts transfer learning to increase the normal feature density so that abnormal features can be clearly distinguished by applying patch descriptor and memory bank to a pre-trained CNN. The proposed method outperforms the previous methods quantitatively and qualitatively. For example, it provides an AUROC score of 99.5% in anomaly detection and 98.5% in anomaly localization of MVTec AD benchmark. In addition, this paper points out the negative effects of biased features of pre-trained CNNs and emphasizes the importance of adaptation to the target dataset.
Subfields: Artificial Intelligence, Computer Networks and Communications, Epidemiology
View Paper: https://www.semanticscholar.org/paper/5de172c1031a38184a431b6e704f040f6f509064
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Nguyen H. Tran
- Anh Tuan Nguyen
- Steven Quoc Hung Truong
- Ming Tang
- Nguyen
- Chanh D. Tr
- Tran Dinh Tien
- Soan Thi Minh Duong
In Computer Networks and Communications
Citations in the corpus
- Deep Industrial Image Anomaly Detection: A Survey (2023, neutral): “CFA [70] SVDD ResNet The paper improves PatchCore so that image features are distributed on a hypersphere.”
- Revisiting Reverse Distillation for Anomaly Detection (2023, methodology): “Recent research in anomaly detection, such as PatchCore [27], and CFA [20], have achieved state-of-the-art performance in detecting and localizing anomalies.”
- AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models (2023, background): “PatchCore [23] and CFA [12] establish a memory bank of patch embeddings from normal samples and detect anomalies by measuring the distance between a test sample embedding and its nearest normal embedding in the memory bank.”